New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Performance Insights

by anthropics in anthropics/commerce-agents

Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales…

OfficialApache-2.0Auto-check passed

Install Performance Insights

skills CLI
$ npx skills add anthropics/commerce-agents --skill performance-insights -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/commerce-agents performance-insights --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/commerce-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/merchant-agent/skills/performance-insights .claude/skills/performance-insights && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
performance-insights
GitHub stars
3.2k
Token cost
~1.4k tokens
SKILL.md length
859 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales…

  • SKILL.md covers Where the figures come from, The comparison, Explaining a movement and Goals and patterns the…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Performance Insights is an agent skill from anthropics/commerce-agents, published by the product's own GitHub organization. Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales, traffic, conversion, and customers or this operation's equivalents that the snapshot alone does not answer. Not needed when the snapshot's headline figures and their change on the prior period answer the question, how a period went included.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Reference blueprint for building shopping and merchant agents with Claude. Examples in retail, commerce, telecom, and entertainment included. The licence is Apache-2.0.

Example prompts

  • “/performance-insights”

What it can do on your machine

Read from SKILL.md and the folder at commit fd4d592. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Performance Insights loads about 1.4k tokens when it runs. Until then it costs about 113 tokens; SKILL.md has 859 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~113
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/commerce-agents at commit fd4d592, republished under its Apache-2.0 licence (© anthropics). 859 words, ~1,401 tokens.

Download SKILL.mdSave it as .claude/skills/performance-insights/SKILL.md (or your agent's skills folder).
name
performance-insights
description
Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales, traffic, conversion, and customers or this operation's equivalents that the snapshot alone does not answer. Not needed when the snapshot's headline figures and their change on the prior period answer the question, how a period went included.

Performance insights

Below, "segment" means whatever unit this operation reports on: a category, a listing, a property, a plan, or an event.

Give the operator a takeaway they can act on, the figure behind it, and the comparison it rests on, and say which reads it came from.

Where the figures come from

  • Start with get_business_snapshot for the period asked about: the headline figures, the prior period (compare_to and the change percentages), and the alert counts that every later figure is read against. Then use query_metrics for one metric over time, narrowed to a segment when the question is about part of the operation.
  • Take margin and stock from get_pricing_context and get_listing, and campaign spend and revenue from get_campaign_performance; the snapshot does not carry them.
  • Report a series the backend does not hold (an error, an empty series, a different metric name than you asked for) as unavailable, and say which question that leaves open.
  • Show a figure you work out from returned data (a run rate, a shortfall, a sell-out date at the current pace) with its inputs beside it.
  • The latest date in a returned series is the latest date the data covers. A period that runs past it is partial; say so before comparing it with a complete one.

The comparison

  • Choose the comparison period for the question and name it: the prior period for how the week went, the same period last year for a swing that could be seasonal, before and after a change when the question is about that change.
  • Compare a partial period with the matching part of the baseline, or say the comparison is partial against complete; give both end dates.
  • When the question is pace against a comparable (this run against the last run of the same thing, or against its peers at the same point in the cycle), fetch the comparable as its own query_metrics series, name it, and say why it is comparable.
  • When the two series came back under different names, put both in present_metrics as returned. When they differ only by period, they share a name: query the current period last, present it, and give the comparable's figures in the text with their period. Either way, state the gap at the same point in the cycle instead of the two totals.
  • When the data holds no comparable (a first run, a first season), say so, give the pace on its own terms, and offer the nearest substitute the data holds, labeled as one. Do not build a comparable from memory of similar cases.
Show full SKILL.md (433 more words)Show less

Explaining a movement

  • Say first what moved, by how much, and against which baseline; then investigate.
  • Confirm the movement before explaining it. A partial period, a gap in the series, or an unusual baseline accounts for many reported drops; when one of those is the explanation, say so and stop.
  • Locate it: query by segment and name the segment that accounts for most of the movement, with its share.
  • Separate mix from level. An average falls when the unit price fell and also when cheaper units made up more of the total; say which one the returned series show, or say that you cannot tell until the segments are queried.
  • Check candidate causes against tool data for the same dates: campaign windows from get_campaign_performance, stockouts or sell-outs from get_inventory_alerts or the listing, price moves from get_pending_changes or a change applied this conversation.
  • Call something the cause only when its timing lines up and the movement sits in the segment it would affect; otherwise report a correlation and name the read that would settle it.
  • Grade your confidence in words that match the evidence: a finding when the data shows it, a lead when it partly does, and "not visible in the data" when nothing does.

Goals and patterns the operator has stated

  • A target stated in this conversation or held in recall_memories turns a summary into a pace report: the figure so far, the share of the period elapsed, and what the rest of the period must average, computed from returned figures. Do not supply a target the operator has not stated.
  • Recall the seasonal patterns the operator has stated before calling a swing unusual, and say which pattern it does or does not fit. Save a goal or pattern stated during this flow with save_memory, so later summaries can pace against it.

Presenting the answer

  • End with present_metrics. Each pick names a measure a tool returned this conversation, under the tool's name for it and with its segment (sales, sales:kids-room, conversion_rate). A single date's value, a difference between two series, and a projection are not picks; they belong in the text.
  • When a present_metrics call is refused as ungrounded, present the retrieved series again with the picks corrected to names the tools returned.
  • Before the component, give the takeaway with its baseline ("sales are down 12% on the prior week, and one category is 9 of those points"), the comparison used, and the one caveat that changes how to read the figures.
  • When the movement traces to something operational, make the last chip the hand-off to the flow that acts on it.

© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in merchant-agent/skills/performance-insights of anthropics/commerce-agents.

Open the folder on GitHubat commit fd4d592

Compare with similar skills

Performance Insights next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Performance Insights compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Performance Insights this skillanthropics/commerce-agents3.2k—~1.4kAutomated safety check: PassApache-2.0
North Star Metricphuryn/pm-skills27k—~1kAutomated safety check: PassMIT
Investigate MetricPostHog/posthog40k—~1.9kAutomated safety check: PassCustom licence
Product Metrics Dashboard Designphuryn/pm-skills27k—~1.3kAutomated safety check: PassMIT
CI Metricspytorch/pytorch104k—~1.1kAutomated safety check: PassCustom licence
Startup Metrics Frameworkwshobson/agents40k—~2.5kAutomated safety check: PassMIT

Similar skills

  • North Star Metric

    phuryn/pm-skills

    Define a North Star Metric and 3-5 supporting input metrics that form a metrics constellation.

    27k GitHub stars~1k tokensUpdated 23 days ago
    Product & Project ManagementAuto-check passed

  • Investigate Metric

    PostHog/posthog

    Official

    Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries.

    40k GitHub stars~1.9k tokensUpdated today
    Product & Project ManagementAuto-check passed

  • Product Metrics Dashboard Design

    phuryn/pm-skills

    Designs a product metrics dashboard: a North Star and input metrics, a definition table with data sources, chart types and alert thresholds, and a screen layout.

    27k GitHub stars~1.3k tokensUpdated 23 days ago
    Product & Project ManagementAuto-check passed

  • CI Metrics

    pytorch/pytorch

    Query PyTorch CI, GitHub Actions, HUD, Grafana, and infrastructure metrics.

    104k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Startup Metrics Framework

    wshobson/agents

    Track, calculate, and optimize key performance metrics for SaaS, marketplace, consumer, and B2B startups from seed through Series A, including unit economics, growth efficiency, and cash management.

    40k GitHub stars~2.5k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed

  • Modeling Activation Metrics

    PostHog/posthog

    Official

    Build reusable activation models — an activation-rate metric and a per-user/per-account activated flag — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated today
    Data & AnalyticsAuto-check passed

More from anthropics/commerce-agents

All 16 skills in this repo

  • Commerce Evals

    anthropics/commerce-agents

    Official

    Authoring and running behavioral evals for a shopping or merchant agent, covering the case shape, authoring rules, code graders and judges, the run pattern, and poisoned fixtures.

    3.2k GitHub stars~1.8k tokensUpdated 6 days ago
    Auto-check passed

  • Catalog Listings

    anthropics/commerce-agents

    Official

    Creating and improving listing content, covering titles, descriptions, attribute completeness, categorization fixes, image callouts written as text, edits written from material the operator…

    3.2k GitHub stars~1k tokensUpdated 6 days ago
    Auto-check passed

  • Commerce Architecture

    anthropics/commerce-agents

    Official

    How the reference commerce agents of either role are structured, covering the loop, where each rule lives, skills, the backend interface, delegates, and model fields.

    3.2k GitHub stars~1.7k tokensUpdated 6 days ago
    Auto-check passed

  • Commerce Merchant Operations

    anthropics/commerce-agents

    Official

    The reference merchant agent, covering its flows, staged changes and host approval, metrics grounding, the analysis delegate, store memory, components, and marketplace rules.

    3.2k GitHub stars~2.1k tokensUpdated 6 days ago
    Auto-check passed

  • Commerce Prompt Caching

    anthropics/commerce-agents

    Official

    The reference agents' cache-stable request assembly, covering the static system and per-request context split, the fixed tool list, the rolling conversation breakpoint, which config fields are…

    3.2k GitHub stars~2k tokensUpdated 6 days ago
    Auto-check passed

  • Commerce Trust Safety

    anthropics/commerce-agents

    Official

    The rules the reference agents enforce in code for third-party content, writes, grounding, identity, and memory, each with its module, plus two adversarial-eval rules.

    3.2k GitHub stars~1.8k tokensUpdated 6 days ago
    Auto-check passed

Questions about Performance Insights

What does Performance Insights do?

Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales…. Performance Insights is an agent skill from anthropics/commerce-agents, published by the product's own GitHub organization. Explaining how the business is doing, meaning why a metric moved, which segment drove it, pace against a comparable, progress against goals the operator has stated, and questions over sales, traffic, conversion, and customers or this operation's equivalents that the snapshot alone does not answer.

How do I install Performance Insights in Claude Code?

Run `npx skills add anthropics/commerce-agents --skill performance-insights -a claude-code`. Or copy the skill folder (merchant-agent/skills/performance-insights in anthropics/commerce-agents) into .claude/skills/performance-insights in your project. Claude Code loads it when a task matches its description.

How do I install Performance Insights in Codex?

Run `npx skills add anthropics/commerce-agents --skill performance-insights -a codex`. Or copy the skill folder (merchant-agent/skills/performance-insights in anthropics/commerce-agents) into .agents/skills/performance-insights in your project. Codex loads it when a task matches its description.

Can I use Performance Insights in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/commerce-agents --skill performance-insights -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/performance-insights, .gemini/skills/performance-insights, .github/skills/performance-insights and .opencode/skills/performance-insights in your project.

What does Performance Insights need to run?

SKILL.md names no scripts, command-line tools or credentials: Performance Insights is instructions for the agent only.

Does Performance Insights access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Performance Insights safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Performance Insights use?

Performance Insights is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Performance Insights use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Performance Insights?

Skills that share tags, products or a category with Performance Insights: North Star Metric (phuryn/pm-skills, 27k stars), Investigate Metric (PostHog/posthog, 40k stars), Product Metrics Dashboard Design (phuryn/pm-skills, 27k stars) and CI Metrics (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Performance Insights?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/commerce-agents, which has 3,179 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 2, 2026.

Source: anthropics/commerce-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.